Qwen: Qwen3 Coder 30B A3B Instruct
microqwen/qwen3-coder-30b-a3b-instruct
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
AA INDEX9.6
CONTEXT262K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED2 min ago
Input
$0.11 /M
Output
$0.44 /M
Blended (40/60)
$0.31 /M
Cost / IQ
$1.2853 /M
Cost / IQ = Blended Price ÷ (AA Intelligence Score ÷ 40). Normalises price by model intelligence so you can compare value across tiers. Lower = better value per unit of intelligence. Not a transactional price.
24h0%
7d0%
Price History
30-day view, daily close
Low: $0.19/M
High: $0.31/M
Average: $0.30/M
Provider Comparison
4 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓Novita | $0.07 | $0.27 | $0.19 | -38.3% |
| SiliconFlow | $0.07 | $0.28 | $0.20 | -36.4% |
| Amazon Bedrock | $0.15 | $0.60 | $0.42 | +36.4% |
| Alibaba | $0.29 | $1.46 | $0.99 | +222.9% |
Blended price = 40% input + 60% output. Median price shown in header is the reference price for this model.
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)$1.2853/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
At or below SIT TPI
Value Ranking (by Cost / IQ)
Rank #498 of 581 micro models
← YOU ARE HERE | Qwen: Qwen3 Coder 30B A3B Instruct
Data Sources
Source
Aggregator & direct provider data
4 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/qwen/qwen3-coder-30b-a3b-instruct
# Response (truncated)
{ "model_id": "qwen/qwen3-coder-30b-a3b-instruct", "name": "Qwen: Qwen3 Coder 30B A3B Instruct", "blended_price_per_m": 0.308, "sit_adjusted_price": 1.285291 }